Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     captcha
    -0.83
    etheless
    -0.82
     pse
    -0.75
     dummy
    -0.74
     narrated
    -0.73
     silence
    -0.73
     trope
    -0.71
     clever
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
     puzz
    -0.68
    POSITIVE LOGITS
     Creek
    1.23
    adelphia
    1.14
    esville
    1.09
     Prairie
    1.03
     Avenue
    1.02
     Harbor
    1.02
    ewater
    1.01
    ona
    1.00
    endale
    0.99
     Lake
    0.99
    Act Density 0.517%

    No Known Activations